Section: New Results

WeBrowse: a Passive Content Curation System Based on HTTP Logs

Participants: Giuseppe Scavo, Zied Ben Houidi (Alcatel-Lucent), Renata Teixeira, Stefano Traverso (Politecnico di Torino), Marco Mellia (Politecnico di Torino)

Content curation refers to the act of assisting users to identify relevant and interesting information in the overwhelming amount of online content available today. Existing curation services rely either on experts or on crowdsourcing to promote content. This work designs, implements, and evaluates WeBrowse, the first passive crowdsourced content curation system. WeBrowse requires no active user engagement to promote content. Instead, it extracts the URLs users visit from traffic traversing an ISP network to identify popular and interesting content. A key challenge to design such a passive curation system is to process network traffic in real-time to identify the small set of URLs that are interesting to users. WeBrowse contains a set of heuristics to identify the set of URLs users visit and to select the subset that are interesting, while preserving their privacy at the same time. We prototype WeBrowse and evaluate it using traces collected at a large European ISP, and in a deployment in a large campus network. We have tested and improved WeBrowse with a small number of users from September 2014 to January 2015. The plan is to announce WeBrowse to all users of the campus network early 2015 to get feedback on their experience with the system.

Available at: http://tstat.polito.it/netcurator/